Peter Szemraj PRO

pszemraj's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 5 hours ago

CGPT: Cluster-Guided Partial Tables with LLM-Generated Supervision for Table Retrieval

Paper • 2601.15849 • Published 7 days ago • 13

upvoted a paper about 6 hours ago

Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability

Paper • 2601.18778 • Published 2 days ago • 26

upvoted a paper about 8 hours ago

Post-LayerNorm Is Back: Stable, ExpressivE, and Deep

Paper • 2601.19895 • Published 1 day ago • 10

upvoted an article about 23 hours ago

view article

Article

Introducing Waypoint-1: Real-time interactive video diffusion from Overworld

• 
• 
• +3

9 days ago

•

31

upvoted 4 papers 3 days ago

Agentic Uncertainty Quantification

Paper • 2601.15703 • Published 7 days ago • 8

Agentic Confidence Calibration

Paper • 2601.15778 • Published 7 days ago • 5

Towards Automated Kernel Generation in the Era of LLMs

Paper • 2601.15727 • Published 7 days ago • 16

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published 12 days ago • 30

upvoted a paper 6 days ago

NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems

Paper • 2601.11004 • Published 13 days ago • 30

upvoted 2 articles 9 days ago

view article

Article

LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family

• 

10 days ago

•

69

view article

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

• 

14 days ago

•

61

upvoted 2 papers 9 days ago

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published 13 days ago • 26

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published 16 days ago • 145

upvoted a paper 11 days ago

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs

Paper • 2601.08763 • Published 16 days ago • 141

upvoted a paper 12 days ago

sui-1: Grounded and Verifiable Long-Form Summarization

Paper • 2601.08472 • Published 16 days ago • 3

upvoted a paper 15 days ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Paper • 2601.05905 • Published 20 days ago • 18

upvoted a collection 15 days ago

💧 LFM2.5

Collection

Collection of Instruct, Base, and Japanese LFM2.5-1.2B models. • 22 items • Updated 2 days ago • 81

upvoted 3 papers about 1 month ago

From Word to World: Can Large Language Models be Implicit Text-based World Models?

Paper • 2512.18832 • Published Dec 21, 2025 • 15

TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior

Paper • 2512.20757 • Published Dec 23, 2025 • 17

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published Dec 24, 2025 • 35